Selective Search
Description
Selective Search is a region proposal algorithm for object detection tasks. It starts by over-segmenting the image based on intensity of the pixels using a graph-based segmentation method by Felzenszwalb and Huttenlocher. Selective Search then takes these oversegments as initial input and performs the following steps
- Add all bounding boxes corresponding to segmented parts to the list of regional proposals
- Group adjacent segments based on similarity
- Go to step 1
At each iteration, larger segments are formed and added to the list of region proposals. Hence we create region proposals from smaller segments to larger segments in a bottom-up approach. This is what we mean by computing “hierarchical” segmentations using Felzenszwalb and Huttenlocher’s oversegments.
Papers Using This Method
A Realistic Protocol for Evaluation of Weakly Supervised Object Localization2024-04-15Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms2022-10-29Super-Resolution Based Patch-Free 3D Image Segmentation with High-Frequency Guidance2022-10-26MICO: Selective Search with Mutual Information Co-training2022-09-09Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning2022-05-09Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning2021-11-26DETReg: Unsupervised Pretraining with Region Priors for Object Detection2021-06-08Aligning Pretraining for Detection via Object-Level Contrastive Learning2021-06-04An Ultra Lightweight CNN for Low Resource Circuit Component Recognition2020-10-01Learning Objectness from Sonar Images for Class-Independent Object Detection2019-07-01You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection2019-06-01RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles2019-05-01Automatic Handgun Detection in X-ray Images using Bag of Words Model with Selective Search2019-03-04Semantic Hierarchical Priors for Intrinsic Image Decomposition2019-02-11Learning Position Evaluation Functions Used in Monte Carlo Softmax Search2019-01-30Deep Multiple Instance Learning for Zero-shot Image Tagging2018-03-16ME R-CNN: Multi-Expert R-CNN for Object Detection2017-04-04Deep Learning the Indus Script2017-02-02A MultiPath Network for Object Detection2016-04-07Diversity in Object Proposals2016-03-14